skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 5:00 PM ET until 11:00 PM ET on Friday, June 21 due to maintenance. We apologize for the inconvenience.


Title: Seiden: Revisiting Query Processing in Video Database Systems

State-of-the-art video database management systems (VDBMSs) often use lightweight proxy models to accelerate object retrieval and aggregate queries. The key assumption underlying these systems is that the proxy model is an order of magnitude faster than the heavyweight oracle model. However, recent advances in computer vision have invalidated this assumption. Inference time of recently proposed oracle models is on par with or even lower than the proxy models used in state-of-the-art (SoTA) VDBMSs. This paper presents Seiden, a VDBMS that leverages this radical shift in the runtime gap between the oracle and proxy models. Instead of relying on a proxy model, Seiden directly applies the oracle model over a subset of frames to build a query-agnostic index, and samples additional frames to answer the query using an exploration-exploitation scheme during query processing. By leveraging the temporal continuity of the video and the output of the oracle model on the sampled frames, Seiden delivers faster query processing and better query accuracy than SoTA VDBMSs. Our empirical evaluation shows that Seiden is on average 6.6 x faster than SoTA VDBMSs across diverse queries and datasets.

 
more » « less
Award ID(s):
2238431
NSF-PAR ID:
10483716
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
VLDB
Date Published:
Journal Name:
Proceedings of the VLDB Endowment
Volume:
16
Issue:
9
ISSN:
2150-8097
Page Range / eLocation ID:
2289 to 2301
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Large volumes of videos are continuously recorded from cameras deployed for traffic control and surveillance with the goal of answering “after the fact” queries: identify video frames with objects of certain classes (cars, bags) from many days of recorded video. Current systems for processing such queries on large video datasets incur either high cost at video ingest time or high latency at query time. We present Focus, a system providing both low-cost and low-latency querying on large video datasets. Focus’s architecture flexibly and effectively divides the query processing work between ingest time and query time. At ingest time (on live videos), Focus uses cheap convolutional network classifiers (CNNs) to construct an approximate index of all possible object classes in each frame (to handle queries for any class in the future). At query time, Focus leverages this approximate index to provide low latency, but compensates for the lower accuracy of the cheap CNNs through the judicious use of an expensive CNN. Experiments on commercial video streams show that Focus is 48× (up to 92×) cheaper than using expensive CNNs for ingestion, and provides 125× (up to 607×) lower query latency than a state-of-the-art video querying system (NoScope). 
    more » « less
  2. null (Ed.)
    Deep learning now offers state-of-the-art accuracy for many prediction tasks. A form of deep learning called deep convolutional neural networks (CNNs) are especially popular on image, video, and time series data. Due to its high computational cost, CNN inference is often a bottleneck in analytics tasks on such data. Thus, a lot of work in the computer architecture, systems, and compilers communities study how to make CNN inference faster. In this work, we show that by elevating the abstraction level and re-imagining CNN inference as queries , we can bring to bear database-style query optimization techniques to improve CNN inference efficiency. We focus on tasks that perform CNN inference repeatedly on inputs that are only slightly different . We identify two popular CNN tasks with this behavior: occlusion-based explanations (OBE) and object recognition in videos (ORV). OBE is a popular method for “explaining” CNN predictions. It outputs a heatmap over the input to show which regions (e.g., image pixels) mattered most for a given prediction. It leads to many re-inference requests on locally modified inputs. ORV uses CNNs to identify and track objects across video frames. It also leads to many re-inference requests. We cast such tasks in a unified manner as a novel instance of the incremental view maintenance problem and create a comprehensive algebraic framework for incremental CNN inference that reduces computational costs. We produce materialized views of features produced inside a CNN and connect them with a novel multi-query optimization scheme for CNN re-inference. Finally, we also devise novel OBE-specific and ORV-specific approximate inference optimizations exploiting their semantics. We prototype our ideas in Python to create a tool called Krypton that supports both CPUs and GPUs. Experiments with real data and CNNs show that Krypton reduces runtimes by up to 5× (respectively, 35×) to produce exact (respectively, high-quality approximate) results without raising resource requirements. 
    more » « less
  3. The goal of this paper is to improve the efficiency and applicability of straightline extraction techniques in the random oracle model. Straightline extraction in the random oracle model refers to the existence of an extractor, which given the random oracle queries made by a prover on some theorem, is able to produce a witness for with roughly the same probability that produces a verifying proof. This notion applies to both zero-knowledge protocols and verifiable computation where the goal is compressing a proof. Pass (CRYPTO '03) first showed how to achieve this property for NP using a cut-and-choose technique which incurred a -bit overhead in communication where is a security parameter. Fischlin (CRYPTO '05) presented a more efficient technique based on ``proofs of work'' that sheds this cost, but only applies to a limited class of Sigma Protocols with a ``quasi-unique response'' property, which for example, does not necessarily include the standard OR composition for Sigma protocols. With Schnorr/EdDSA signature aggregation as a motivating application, we develop new techniques to improve the computation cost of straight-line extractable proofs. Our improvements to the state of the art range from 70X--200X for the best compression parameters. This is due to a uniquely suited polynomial evaluation algorithm, and the insight that a proof-of-work that relies on multicollisions and the birthday paradox is faster to solve than inverting a fixed target. Our collision based proof-of-work more generally improves the Prover's random oracle query complexity when applied in the NIZK setting as well. In addition to reducing the query complexity of Fischlin's Prover, for a special class of Sigma protocols we can for the first time closely match a new lower bound we present. Finally we extend Fischlin's technique so that it applies to a more general class of strongly-sound Sigma protocols, which includes the OR composition. We achieve this by carefully randomizing Fischlin's technique---we show that its current deterministic nature prevents its application to certain multi-witness languages. 
    more » « less
  4. We will demonstrate a prototype query-processing engine, which utilizes correlations among predicates to accelerate machine learning (ML) inference queries on unstructured data. Expensive operators such as feature extractors and classifiers are deployed as user-defined functions (UDFs), which are not penetrable by classic query optimization techniques such as predicate push-down. Recent optimization schemes (e.g., Probabilistic Predicates or PP) build a cheap proxy model for each predicate offline, and inject proxy models in the front of expensive ML UDFs under the independence assumption in queries. Input records that do not satisfy query predicates are filtered early by proxy models to bypass ML UDFs. But enforcing the independence assumption may result in sub-optimal plans. We use correlative proxy models to better exploit predicate correlations and accelerate ML queries. We will demonstrate our query optimizer called CORE, which builds proxy models online, allocates parameters to each model, and reorders them. We will also show end-to-end query processing with or without proxy models. 
    more » « less
  5. We consider accelerating machine learning (ML) inference queries on unstructured datasets. Expensive operators such as feature extractors and classifiers are deployed as user-defined functions (UDFs), which are not penetrable with classic query optimization techniques such as predicate push-down. Recent optimization schemes (e.g., Probabilistic Predicates or PP) assume independence among the query predicates, build a proxy model for each predicate offline, and rewrite a new query by injecting these cheap proxy models in the front of the expensive ML UDFs. In such a manner, unlikely inputs that do not satisfy query predicates are filtered early to bypass the ML UDFs. We show that enforcing the independence assumption in this context may result in sub-optimal plans. In this paper, we propose CORE, a query optimizer that better exploits the predicate correlations and accelerates ML inference queries. Our solution builds the proxy models online for a new query and leverages a branch-and-bound search process to reduce the building costs. Results on three real-world text, image and video datasets show that CORE improves the query throughput by up to 63% compared to PP and up to 80% compared to running the queries as it is. 
    more » « less